Glutton-zh
Glutton-zh
i have the same environment and error,have you solved it? can I get some help?
@Hello526
i use CenterNet to train VOC2007,but it's break at 79748/180000 (at 64th epoch). i try again and break at 68364/180000 again. my gpu memory-usage is 8051mib/5116mib. and the error is:...
@diamour @chong-zheng i use CenterNet and has the same error, i had been read the issues in CenterNet,CornerNet and CornerNet-Lite, but i still dont see the answer. cuda10, torch1.0, torchvision0.2.1,...
up to now, Is there an effective solution to this problem——use the bach_size == 1;
Have you solved the problem i use it on voc2007 and get loading parameters at iteration: 225000 building neural network... module_file: models.CenterNet-52 total parameters: 104797892 loading parameters... loading model from...
i train on voc2007 too but i just get a rusult.json but map, how can i get the map about my model